nerui-pt-pl30-1 / trainer_state.json
apwic's picture
End of training
b2c1429 verified
raw
history blame
111 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 100.0,
"eval_steps": 500,
"global_step": 9600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 1.0983918905258179,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.8833,
"step": 96
},
{
"epoch": 1.0,
"eval_LOCATION_f1": 0.0,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.0,
"eval_LOCATION_recall": 0.0,
"eval_ORGANIZATION_f1": 0.15813953488372093,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.2982456140350877,
"eval_ORGANIZATION_recall": 0.10759493670886076,
"eval_PERSON_f1": 0.16949152542372883,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.2830188679245283,
"eval_PERSON_recall": 0.12096774193548387,
"eval_loss": 0.4193257987499237,
"eval_overall_accuracy": 0.850123524567664,
"eval_overall_f1": 0.12549019607843137,
"eval_overall_precision": 0.2857142857142857,
"eval_overall_recall": 0.08040201005025126,
"eval_runtime": 0.6481,
"eval_samples_per_second": 262.311,
"eval_steps_per_second": 4.629,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 0.8533632159233093,
"learning_rate": 4.9e-05,
"loss": 0.3788,
"step": 192
},
{
"epoch": 2.0,
"eval_LOCATION_f1": 0.3568464730290456,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.344,
"eval_LOCATION_recall": 0.3706896551724138,
"eval_ORGANIZATION_f1": 0.555205047318612,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.5534591194968553,
"eval_ORGANIZATION_recall": 0.5569620253164557,
"eval_PERSON_f1": 0.6416382252559727,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.5562130177514792,
"eval_PERSON_recall": 0.7580645161290323,
"eval_loss": 0.23748576641082764,
"eval_overall_accuracy": 0.9286302497941257,
"eval_overall_f1": 0.5287896592244419,
"eval_overall_precision": 0.4966887417218543,
"eval_overall_recall": 0.5653266331658291,
"eval_runtime": 0.6694,
"eval_samples_per_second": 253.971,
"eval_steps_per_second": 4.482,
"step": 192
},
{
"epoch": 3.0,
"grad_norm": 0.8952131271362305,
"learning_rate": 4.85e-05,
"loss": 0.2233,
"step": 288
},
{
"epoch": 3.0,
"eval_LOCATION_f1": 0.7325102880658436,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.7007874015748031,
"eval_LOCATION_recall": 0.7672413793103449,
"eval_ORGANIZATION_f1": 0.7172011661807581,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.6648648648648648,
"eval_ORGANIZATION_recall": 0.7784810126582279,
"eval_PERSON_f1": 0.9307692307692308,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.8897058823529411,
"eval_PERSON_recall": 0.9758064516129032,
"eval_loss": 0.12203584611415863,
"eval_overall_accuracy": 0.9618446335437826,
"eval_overall_f1": 0.7872340425531915,
"eval_overall_precision": 0.7433035714285714,
"eval_overall_recall": 0.8366834170854272,
"eval_runtime": 0.6919,
"eval_samples_per_second": 245.689,
"eval_steps_per_second": 4.336,
"step": 288
},
{
"epoch": 4.0,
"grad_norm": 1.2461464405059814,
"learning_rate": 4.8e-05,
"loss": 0.1473,
"step": 384
},
{
"epoch": 4.0,
"eval_LOCATION_f1": 0.8267716535433071,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.7608695652173914,
"eval_LOCATION_recall": 0.9051724137931034,
"eval_ORGANIZATION_f1": 0.7905604719764011,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.7403314917127072,
"eval_ORGANIZATION_recall": 0.8481012658227848,
"eval_PERSON_f1": 0.9799196787148594,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.976,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.09417078644037247,
"eval_overall_accuracy": 0.9711776008783969,
"eval_overall_f1": 0.8574821852731591,
"eval_overall_precision": 0.8130630630630631,
"eval_overall_recall": 0.907035175879397,
"eval_runtime": 0.6786,
"eval_samples_per_second": 250.509,
"eval_steps_per_second": 4.421,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 0.5030807852745056,
"learning_rate": 4.75e-05,
"loss": 0.118,
"step": 480
},
{
"epoch": 5.0,
"eval_LOCATION_f1": 0.8908296943231441,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9026548672566371,
"eval_LOCATION_recall": 0.8793103448275862,
"eval_ORGANIZATION_f1": 0.8711656441717791,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.8452380952380952,
"eval_ORGANIZATION_recall": 0.8987341772151899,
"eval_PERSON_f1": 0.976,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9682539682539683,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.06021573767066002,
"eval_overall_accuracy": 0.9821575624485315,
"eval_overall_f1": 0.9093167701863355,
"eval_overall_precision": 0.8992628992628993,
"eval_overall_recall": 0.9195979899497487,
"eval_runtime": 0.659,
"eval_samples_per_second": 257.953,
"eval_steps_per_second": 4.552,
"step": 480
},
{
"epoch": 6.0,
"grad_norm": 1.139099359512329,
"learning_rate": 4.7e-05,
"loss": 0.1004,
"step": 576
},
{
"epoch": 6.0,
"eval_LOCATION_f1": 0.8595041322314049,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8253968253968254,
"eval_LOCATION_recall": 0.896551724137931,
"eval_ORGANIZATION_f1": 0.8817891373801917,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.8903225806451613,
"eval_ORGANIZATION_recall": 0.8734177215189873,
"eval_PERSON_f1": 0.9644268774703558,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9457364341085271,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.05802244320511818,
"eval_overall_accuracy": 0.9807850672522647,
"eval_overall_f1": 0.9009900990099009,
"eval_overall_precision": 0.8878048780487805,
"eval_overall_recall": 0.914572864321608,
"eval_runtime": 0.6551,
"eval_samples_per_second": 259.521,
"eval_steps_per_second": 4.58,
"step": 576
},
{
"epoch": 7.0,
"grad_norm": 0.9177888035774231,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.0894,
"step": 672
},
{
"epoch": 7.0,
"eval_LOCATION_f1": 0.8849557522123893,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.8620689655172413,
"eval_ORGANIZATION_f1": 0.88,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.8562874251497006,
"eval_ORGANIZATION_recall": 0.9050632911392406,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.050588276237249374,
"eval_overall_accuracy": 0.9824320614877848,
"eval_overall_f1": 0.9138576779026217,
"eval_overall_precision": 0.9081885856079405,
"eval_overall_recall": 0.9195979899497487,
"eval_runtime": 0.6493,
"eval_samples_per_second": 261.808,
"eval_steps_per_second": 4.62,
"step": 672
},
{
"epoch": 8.0,
"grad_norm": 0.8791161775588989,
"learning_rate": 4.600000000000001e-05,
"loss": 0.078,
"step": 768
},
{
"epoch": 8.0,
"eval_LOCATION_f1": 0.887029288702929,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8617886178861789,
"eval_LOCATION_recall": 0.9137931034482759,
"eval_ORGANIZATION_f1": 0.8974358974358974,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9090909090909091,
"eval_ORGANIZATION_recall": 0.8860759493670886,
"eval_PERSON_f1": 0.9799196787148594,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.976,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.04895670339465141,
"eval_overall_accuracy": 0.984079055723305,
"eval_overall_f1": 0.92,
"eval_overall_precision": 0.9154228855721394,
"eval_overall_recall": 0.9246231155778895,
"eval_runtime": 0.6614,
"eval_samples_per_second": 257.033,
"eval_steps_per_second": 4.536,
"step": 768
},
{
"epoch": 9.0,
"grad_norm": 0.5338044166564941,
"learning_rate": 4.55e-05,
"loss": 0.0717,
"step": 864
},
{
"epoch": 9.0,
"eval_LOCATION_f1": 0.8991596638655462,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8770491803278688,
"eval_LOCATION_recall": 0.9224137931034483,
"eval_ORGANIZATION_f1": 0.8944099378881988,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.8780487804878049,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9838709677419355,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9838709677419355,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.051603902131319046,
"eval_overall_accuracy": 0.9849025528410651,
"eval_overall_f1": 0.9232673267326732,
"eval_overall_precision": 0.9097560975609756,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.6605,
"eval_samples_per_second": 257.38,
"eval_steps_per_second": 4.542,
"step": 864
},
{
"epoch": 10.0,
"grad_norm": 0.6841580271720886,
"learning_rate": 4.5e-05,
"loss": 0.067,
"step": 960
},
{
"epoch": 10.0,
"eval_LOCATION_f1": 0.8995983935742972,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8421052631578947,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.8918032786885246,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9251700680272109,
"eval_ORGANIZATION_recall": 0.8607594936708861,
"eval_PERSON_f1": 0.9647058823529411,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9389312977099237,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.054757531732320786,
"eval_overall_accuracy": 0.9805105682130113,
"eval_overall_f1": 0.9171817058096415,
"eval_overall_precision": 0.902676399026764,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.6672,
"eval_samples_per_second": 254.793,
"eval_steps_per_second": 4.496,
"step": 960
},
{
"epoch": 11.0,
"grad_norm": 0.6890102624893188,
"learning_rate": 4.4500000000000004e-05,
"loss": 0.065,
"step": 1056
},
{
"epoch": 11.0,
"eval_LOCATION_f1": 0.9135802469135803,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8740157480314961,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9235668789808917,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9294871794871795,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04228746518492699,
"eval_overall_accuracy": 0.987098545155092,
"eval_overall_f1": 0.9404466501240695,
"eval_overall_precision": 0.928921568627451,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.7244,
"eval_samples_per_second": 234.674,
"eval_steps_per_second": 4.141,
"step": 1056
},
{
"epoch": 12.0,
"grad_norm": 0.5224666595458984,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.0574,
"step": 1152
},
{
"epoch": 12.0,
"eval_LOCATION_f1": 0.9106382978723405,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8991596638655462,
"eval_LOCATION_recall": 0.9224137931034483,
"eval_ORGANIZATION_f1": 0.9220779220779222,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9466666666666667,
"eval_ORGANIZATION_recall": 0.8987341772151899,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03788928687572479,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9393939393939393,
"eval_overall_precision": 0.9441624365482234,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.6665,
"eval_samples_per_second": 255.075,
"eval_steps_per_second": 4.501,
"step": 1152
},
{
"epoch": 13.0,
"grad_norm": 0.48659205436706543,
"learning_rate": 4.35e-05,
"loss": 0.0559,
"step": 1248
},
{
"epoch": 13.0,
"eval_LOCATION_f1": 0.9316239316239315,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.923728813559322,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9274447949526813,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9245283018867925,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04060617461800575,
"eval_overall_accuracy": 0.9881965413121054,
"eval_overall_f1": 0.9475,
"eval_overall_precision": 0.9427860696517413,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6528,
"eval_samples_per_second": 260.402,
"eval_steps_per_second": 4.595,
"step": 1248
},
{
"epoch": 14.0,
"grad_norm": 0.4807557761669159,
"learning_rate": 4.3e-05,
"loss": 0.0508,
"step": 1344
},
{
"epoch": 14.0,
"eval_LOCATION_f1": 0.9243697478991596,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9016393442622951,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9225806451612903,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9407894736842105,
"eval_ORGANIZATION_recall": 0.9050632911392406,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04647667706012726,
"eval_overall_accuracy": 0.9876475432335987,
"eval_overall_f1": 0.9423558897243106,
"eval_overall_precision": 0.94,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.66,
"eval_samples_per_second": 257.56,
"eval_steps_per_second": 4.545,
"step": 1344
},
{
"epoch": 15.0,
"grad_norm": 0.6128695011138916,
"learning_rate": 4.25e-05,
"loss": 0.0474,
"step": 1440
},
{
"epoch": 15.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9308176100628932,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.925,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04079201817512512,
"eval_overall_accuracy": 0.9876475432335987,
"eval_overall_f1": 0.9514321295143213,
"eval_overall_precision": 0.9432098765432099,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.6635,
"eval_samples_per_second": 256.216,
"eval_steps_per_second": 4.521,
"step": 1440
},
{
"epoch": 16.0,
"grad_norm": 0.9973705410957336,
"learning_rate": 4.2e-05,
"loss": 0.0458,
"step": 1536
},
{
"epoch": 16.0,
"eval_LOCATION_f1": 0.94017094017094,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9322033898305084,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.939297124600639,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9483870967741935,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03876470774412155,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9535759096612295,
"eval_overall_precision": 0.9523809523809523,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6544,
"eval_samples_per_second": 259.784,
"eval_steps_per_second": 4.584,
"step": 1536
},
{
"epoch": 17.0,
"grad_norm": 0.8017911314964294,
"learning_rate": 4.15e-05,
"loss": 0.0456,
"step": 1632
},
{
"epoch": 17.0,
"eval_LOCATION_f1": 0.9237288135593221,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9083333333333333,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9221183800623053,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9079754601226994,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04639029502868652,
"eval_overall_accuracy": 0.9876475432335987,
"eval_overall_f1": 0.9417596034696406,
"eval_overall_precision": 0.9290953545232273,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6533,
"eval_samples_per_second": 260.228,
"eval_steps_per_second": 4.592,
"step": 1632
},
{
"epoch": 18.0,
"grad_norm": 0.38305139541625977,
"learning_rate": 4.1e-05,
"loss": 0.0436,
"step": 1728
},
{
"epoch": 18.0,
"eval_LOCATION_f1": 0.94017094017094,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9322033898305084,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9517684887459807,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9673202614379085,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03976227343082428,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9584905660377357,
"eval_overall_precision": 0.9596977329974811,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6639,
"eval_samples_per_second": 256.073,
"eval_steps_per_second": 4.519,
"step": 1728
},
{
"epoch": 19.0,
"grad_norm": 0.7068957090377808,
"learning_rate": 4.05e-05,
"loss": 0.0412,
"step": 1824
},
{
"epoch": 19.0,
"eval_LOCATION_f1": 0.9437229437229439,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9478260869565217,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9308176100628932,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.925,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.042109083384275436,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.95,
"eval_overall_precision": 0.945273631840796,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6635,
"eval_samples_per_second": 256.232,
"eval_steps_per_second": 4.522,
"step": 1824
},
{
"epoch": 20.0,
"grad_norm": 0.5367431044578552,
"learning_rate": 4e-05,
"loss": 0.0384,
"step": 1920
},
{
"epoch": 20.0,
"eval_LOCATION_f1": 0.9021276595744682,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8907563025210085,
"eval_LOCATION_recall": 0.9137931034482759,
"eval_ORGANIZATION_f1": 0.923076923076923,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.8982035928143712,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04670054465532303,
"eval_overall_accuracy": 0.9873730441943454,
"eval_overall_f1": 0.9346485819975339,
"eval_overall_precision": 0.9176755447941889,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6597,
"eval_samples_per_second": 257.707,
"eval_steps_per_second": 4.548,
"step": 1920
},
{
"epoch": 21.0,
"grad_norm": 0.9570126533508301,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.0369,
"step": 2016
},
{
"epoch": 21.0,
"eval_LOCATION_f1": 0.9237288135593221,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9083333333333333,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9337539432176657,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9308176100628931,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.041418496519327164,
"eval_overall_accuracy": 0.9892945374691189,
"eval_overall_f1": 0.945273631840796,
"eval_overall_precision": 0.9359605911330049,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.664,
"eval_samples_per_second": 256.037,
"eval_steps_per_second": 4.518,
"step": 2016
},
{
"epoch": 22.0,
"grad_norm": 0.7272740006446838,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.0332,
"step": 2112
},
{
"epoch": 22.0,
"eval_LOCATION_f1": 0.9152542372881356,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9363057324840764,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9423076923076923,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04091789945960045,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.9450000000000001,
"eval_overall_precision": 0.9402985074626866,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.6625,
"eval_samples_per_second": 256.594,
"eval_steps_per_second": 4.528,
"step": 2112
},
{
"epoch": 23.0,
"grad_norm": 0.8585413098335266,
"learning_rate": 3.85e-05,
"loss": 0.035,
"step": 2208
},
{
"epoch": 23.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9487179487179488,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.961038961038961,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03734458610415459,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9560853199498118,
"eval_overall_precision": 0.9548872180451128,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6526,
"eval_samples_per_second": 260.507,
"eval_steps_per_second": 4.597,
"step": 2208
},
{
"epoch": 24.0,
"grad_norm": 0.40438827872276306,
"learning_rate": 3.8e-05,
"loss": 0.0338,
"step": 2304
},
{
"epoch": 24.0,
"eval_LOCATION_f1": 0.9282700421940928,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9463722397476341,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9433962264150944,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04183060675859451,
"eval_overall_accuracy": 0.9884710403513588,
"eval_overall_f1": 0.9527363184079602,
"eval_overall_precision": 0.9433497536945813,
"eval_overall_recall": 0.9623115577889447,
"eval_runtime": 0.6702,
"eval_samples_per_second": 253.639,
"eval_steps_per_second": 4.476,
"step": 2304
},
{
"epoch": 25.0,
"grad_norm": 0.5789974331855774,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0331,
"step": 2400
},
{
"epoch": 25.0,
"eval_LOCATION_f1": 0.9276595744680851,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9159663865546218,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9137380191693291,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9225806451612903,
"eval_ORGANIZATION_recall": 0.9050632911392406,
"eval_PERSON_f1": 0.9761904761904763,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9609375,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04574756324291229,
"eval_overall_accuracy": 0.9876475432335987,
"eval_overall_f1": 0.9375,
"eval_overall_precision": 0.9328358208955224,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.6499,
"eval_samples_per_second": 261.578,
"eval_steps_per_second": 4.616,
"step": 2400
},
{
"epoch": 26.0,
"grad_norm": 0.18414248526096344,
"learning_rate": 3.7e-05,
"loss": 0.0287,
"step": 2496
},
{
"epoch": 26.0,
"eval_LOCATION_f1": 0.9282700421940928,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9260450160771704,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9411764705882353,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.048786915838718414,
"eval_overall_accuracy": 0.9881965413121054,
"eval_overall_f1": 0.9436795994993743,
"eval_overall_precision": 0.940149625935162,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.6652,
"eval_samples_per_second": 255.55,
"eval_steps_per_second": 4.51,
"step": 2496
},
{
"epoch": 27.0,
"grad_norm": 0.7831467390060425,
"learning_rate": 3.65e-05,
"loss": 0.0282,
"step": 2592
},
{
"epoch": 27.0,
"eval_LOCATION_f1": 0.9276595744680851,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9159663865546218,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9290322580645162,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9473684210526315,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.976,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9682539682539683,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.046819597482681274,
"eval_overall_accuracy": 0.9879220422728521,
"eval_overall_f1": 0.9433962264150944,
"eval_overall_precision": 0.9445843828715366,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.6628,
"eval_samples_per_second": 256.477,
"eval_steps_per_second": 4.526,
"step": 2592
},
{
"epoch": 28.0,
"grad_norm": 0.34282711148262024,
"learning_rate": 3.6e-05,
"loss": 0.0282,
"step": 2688
},
{
"epoch": 28.0,
"eval_LOCATION_f1": 0.9191489361702128,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.907563025210084,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9493670886075949,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9493670886075949,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04330836609005928,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9501246882793017,
"eval_overall_precision": 0.943069306930693,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6576,
"eval_samples_per_second": 258.501,
"eval_steps_per_second": 4.562,
"step": 2688
},
{
"epoch": 29.0,
"grad_norm": 0.2705739438533783,
"learning_rate": 3.55e-05,
"loss": 0.0267,
"step": 2784
},
{
"epoch": 29.0,
"eval_LOCATION_f1": 0.9191489361702128,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.907563025210084,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9400630914826499,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9371069182389937,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9761904761904763,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9609375,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.0431785024702549,
"eval_overall_accuracy": 0.9884710403513588,
"eval_overall_f1": 0.945273631840796,
"eval_overall_precision": 0.9359605911330049,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6538,
"eval_samples_per_second": 260.027,
"eval_steps_per_second": 4.589,
"step": 2784
},
{
"epoch": 30.0,
"grad_norm": 0.7205470204353333,
"learning_rate": 3.5e-05,
"loss": 0.0252,
"step": 2880
},
{
"epoch": 30.0,
"eval_LOCATION_f1": 0.927038626609442,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9230769230769231,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9341692789968652,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9254658385093167,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04438180848956108,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9476309226932669,
"eval_overall_precision": 0.9405940594059405,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6599,
"eval_samples_per_second": 257.618,
"eval_steps_per_second": 4.546,
"step": 2880
},
{
"epoch": 31.0,
"grad_norm": 0.4720001518726349,
"learning_rate": 3.45e-05,
"loss": 0.0238,
"step": 2976
},
{
"epoch": 31.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9426751592356688,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9487179487179487,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04321155697107315,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9535759096612295,
"eval_overall_precision": 0.9523809523809523,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6644,
"eval_samples_per_second": 255.871,
"eval_steps_per_second": 4.515,
"step": 2976
},
{
"epoch": 32.0,
"grad_norm": 0.413986474275589,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.0228,
"step": 3072
},
{
"epoch": 32.0,
"eval_LOCATION_f1": 0.9316239316239315,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.923728813559322,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9426751592356688,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9487179487179487,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04056137800216675,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9523809523809523,
"eval_overall_precision": 0.95,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6704,
"eval_samples_per_second": 253.569,
"eval_steps_per_second": 4.475,
"step": 3072
},
{
"epoch": 33.0,
"grad_norm": 0.4109013080596924,
"learning_rate": 3.35e-05,
"loss": 0.0231,
"step": 3168
},
{
"epoch": 33.0,
"eval_LOCATION_f1": 0.9282700421940928,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.932475884244373,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9477124183006536,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9799196787148594,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.976,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.0506090447306633,
"eval_overall_accuracy": 0.9892945374691189,
"eval_overall_f1": 0.9460476787954831,
"eval_overall_precision": 0.9448621553884712,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.6594,
"eval_samples_per_second": 257.815,
"eval_steps_per_second": 4.55,
"step": 3168
},
{
"epoch": 34.0,
"grad_norm": 0.17830440402030945,
"learning_rate": 3.3e-05,
"loss": 0.0219,
"step": 3264
},
{
"epoch": 34.0,
"eval_LOCATION_f1": 0.9310344827586207,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9310344827586207,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9493670886075949,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9493670886075949,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9680000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9603174603174603,
"eval_PERSON_recall": 0.9758064516129032,
"eval_loss": 0.04699116572737694,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9498746867167919,
"eval_overall_precision": 0.9475,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.668,
"eval_samples_per_second": 254.485,
"eval_steps_per_second": 4.491,
"step": 3264
},
{
"epoch": 35.0,
"grad_norm": 0.3655734062194824,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.021,
"step": 3360
},
{
"epoch": 35.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9426751592356688,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9487179487179487,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.976,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9682539682539683,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.04767649993300438,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9510664993726474,
"eval_overall_precision": 0.949874686716792,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6583,
"eval_samples_per_second": 258.256,
"eval_steps_per_second": 4.557,
"step": 3360
},
{
"epoch": 36.0,
"grad_norm": 0.7497072219848633,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.0192,
"step": 3456
},
{
"epoch": 36.0,
"eval_LOCATION_f1": 0.9327731092436975,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9098360655737705,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9385113268608414,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9602649006622517,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.976,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9682539682539683,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.05298491194844246,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9485570890840652,
"eval_overall_precision": 0.9473684210526315,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.6598,
"eval_samples_per_second": 257.661,
"eval_steps_per_second": 4.547,
"step": 3456
},
{
"epoch": 37.0,
"grad_norm": 0.31958967447280884,
"learning_rate": 3.15e-05,
"loss": 0.0208,
"step": 3552
},
{
"epoch": 37.0,
"eval_LOCATION_f1": 0.9237288135593221,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9083333333333333,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9294871794871796,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9415584415584416,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.045642875134944916,
"eval_overall_accuracy": 0.9892945374691189,
"eval_overall_f1": 0.9448621553884713,
"eval_overall_precision": 0.9425,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.7275,
"eval_samples_per_second": 233.667,
"eval_steps_per_second": 4.124,
"step": 3552
},
{
"epoch": 38.0,
"grad_norm": 0.11552680283784866,
"learning_rate": 3.1e-05,
"loss": 0.0193,
"step": 3648
},
{
"epoch": 38.0,
"eval_LOCATION_f1": 0.9282700421940928,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9487179487179488,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.961038961038961,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04232772812247276,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9536921151439299,
"eval_overall_precision": 0.9501246882793017,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6553,
"eval_samples_per_second": 259.442,
"eval_steps_per_second": 4.578,
"step": 3648
},
{
"epoch": 39.0,
"grad_norm": 0.048592615872621536,
"learning_rate": 3.05e-05,
"loss": 0.0181,
"step": 3744
},
{
"epoch": 39.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.952076677316294,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9612903225806452,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.041699863970279694,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9573934837092732,
"eval_overall_precision": 0.955,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.6572,
"eval_samples_per_second": 258.689,
"eval_steps_per_second": 4.565,
"step": 3744
},
{
"epoch": 40.0,
"grad_norm": 0.6681050062179565,
"learning_rate": 3e-05,
"loss": 0.0196,
"step": 3840
},
{
"epoch": 40.0,
"eval_LOCATION_f1": 0.9276595744680851,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9159663865546218,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9493670886075949,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9493670886075949,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.046430543065071106,
"eval_overall_accuracy": 0.9898435355476256,
"eval_overall_f1": 0.9538077403245941,
"eval_overall_precision": 0.9478908188585607,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.6581,
"eval_samples_per_second": 258.305,
"eval_steps_per_second": 4.558,
"step": 3840
},
{
"epoch": 41.0,
"grad_norm": 0.7350420951843262,
"learning_rate": 2.95e-05,
"loss": 0.0179,
"step": 3936
},
{
"epoch": 41.0,
"eval_LOCATION_f1": 0.9237288135593221,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9083333333333333,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.939297124600639,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9483870967741935,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.044399820268154144,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9486858573216519,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6647,
"eval_samples_per_second": 255.76,
"eval_steps_per_second": 4.513,
"step": 3936
},
{
"epoch": 42.0,
"grad_norm": 0.10207242518663406,
"learning_rate": 2.9e-05,
"loss": 0.018,
"step": 4032
},
{
"epoch": 42.0,
"eval_LOCATION_f1": 0.9191489361702128,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.907563025210084,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05390319973230362,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9460476787954831,
"eval_overall_precision": 0.9448621553884712,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.7169,
"eval_samples_per_second": 237.149,
"eval_steps_per_second": 4.185,
"step": 4032
},
{
"epoch": 43.0,
"grad_norm": 0.463298499584198,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.017,
"step": 4128
},
{
"epoch": 43.0,
"eval_LOCATION_f1": 0.935064935064935,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9391304347826087,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9523809523809524,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9554140127388535,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.042005907744169235,
"eval_overall_accuracy": 0.9914905297831458,
"eval_overall_f1": 0.9560853199498118,
"eval_overall_precision": 0.9548872180451128,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6739,
"eval_samples_per_second": 252.257,
"eval_steps_per_second": 4.452,
"step": 4128
},
{
"epoch": 44.0,
"grad_norm": 0.48095300793647766,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.0153,
"step": 4224
},
{
"epoch": 44.0,
"eval_LOCATION_f1": 0.927038626609442,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9230769230769231,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9423076923076923,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9545454545454546,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9761904761904763,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9609375,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05050055682659149,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9485570890840652,
"eval_overall_precision": 0.9473684210526315,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.6638,
"eval_samples_per_second": 256.093,
"eval_steps_per_second": 4.519,
"step": 4224
},
{
"epoch": 45.0,
"grad_norm": 1.063321828842163,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.0162,
"step": 4320
},
{
"epoch": 45.0,
"eval_LOCATION_f1": 0.9106382978723405,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8991596638655462,
"eval_LOCATION_recall": 0.9224137931034483,
"eval_ORGANIZATION_f1": 0.9490445859872612,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9551282051282052,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.049581851810216904,
"eval_overall_accuracy": 0.9898435355476256,
"eval_overall_f1": 0.9486858573216519,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6721,
"eval_samples_per_second": 252.936,
"eval_steps_per_second": 4.464,
"step": 4320
},
{
"epoch": 46.0,
"grad_norm": 0.6382011771202087,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.0162,
"step": 4416
},
{
"epoch": 46.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9419354838709677,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9605263157894737,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04788454994559288,
"eval_overall_accuracy": 0.9898435355476256,
"eval_overall_f1": 0.9522613065326633,
"eval_overall_precision": 0.9522613065326633,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6593,
"eval_samples_per_second": 257.843,
"eval_steps_per_second": 4.55,
"step": 4416
},
{
"epoch": 47.0,
"grad_norm": 0.5830926895141602,
"learning_rate": 2.6500000000000004e-05,
"loss": 0.018,
"step": 4512
},
{
"epoch": 47.0,
"eval_LOCATION_f1": 0.927038626609442,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9230769230769231,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9177215189873418,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9177215189873418,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.046598758548498154,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9411764705882354,
"eval_overall_precision": 0.9376558603491272,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.6604,
"eval_samples_per_second": 257.403,
"eval_steps_per_second": 4.542,
"step": 4512
},
{
"epoch": 48.0,
"grad_norm": 0.22102829813957214,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.0164,
"step": 4608
},
{
"epoch": 48.0,
"eval_LOCATION_f1": 0.9316239316239315,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.923728813559322,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04757728427648544,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.950943396226415,
"eval_overall_precision": 0.9521410579345088,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.6511,
"eval_samples_per_second": 261.084,
"eval_steps_per_second": 4.607,
"step": 4608
},
{
"epoch": 49.0,
"grad_norm": 0.45237526297569275,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.015,
"step": 4704
},
{
"epoch": 49.0,
"eval_LOCATION_f1": 0.9316239316239315,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.923728813559322,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.952076677316294,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9612903225806452,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04722825065255165,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9560853199498118,
"eval_overall_precision": 0.9548872180451128,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6622,
"eval_samples_per_second": 256.738,
"eval_steps_per_second": 4.531,
"step": 4704
},
{
"epoch": 50.0,
"grad_norm": 0.19552862644195557,
"learning_rate": 2.5e-05,
"loss": 0.0138,
"step": 4800
},
{
"epoch": 50.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9423076923076923,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9545454545454546,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04708809405565262,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9534591194968555,
"eval_overall_precision": 0.9546599496221663,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6586,
"eval_samples_per_second": 258.108,
"eval_steps_per_second": 4.555,
"step": 4800
},
{
"epoch": 51.0,
"grad_norm": 0.7048611640930176,
"learning_rate": 2.45e-05,
"loss": 0.0149,
"step": 4896
},
{
"epoch": 51.0,
"eval_LOCATION_f1": 0.9276595744680851,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9159663865546218,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9483870967741935,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9671052631578947,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.050142187625169754,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9534591194968555,
"eval_overall_precision": 0.9546599496221663,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6524,
"eval_samples_per_second": 260.558,
"eval_steps_per_second": 4.598,
"step": 4896
},
{
"epoch": 52.0,
"grad_norm": 0.38548043370246887,
"learning_rate": 2.4e-05,
"loss": 0.0148,
"step": 4992
},
{
"epoch": 52.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9423076923076923,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9545454545454546,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04333503544330597,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9535759096612295,
"eval_overall_precision": 0.9523809523809523,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6616,
"eval_samples_per_second": 256.947,
"eval_steps_per_second": 4.534,
"step": 4992
},
{
"epoch": 53.0,
"grad_norm": 0.18240255117416382,
"learning_rate": 2.35e-05,
"loss": 0.0149,
"step": 5088
},
{
"epoch": 53.0,
"eval_LOCATION_f1": 0.923076923076923,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9152542372881356,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04465426877140999,
"eval_overall_accuracy": 0.9898435355476256,
"eval_overall_f1": 0.9472361809045227,
"eval_overall_precision": 0.9472361809045227,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.6531,
"eval_samples_per_second": 260.278,
"eval_steps_per_second": 4.593,
"step": 5088
},
{
"epoch": 54.0,
"grad_norm": 0.48459962010383606,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.0144,
"step": 5184
},
{
"epoch": 54.0,
"eval_LOCATION_f1": 0.94017094017094,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9322033898305084,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9487179487179488,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.961038961038961,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04604146629571915,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9560853199498118,
"eval_overall_precision": 0.9548872180451128,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6571,
"eval_samples_per_second": 258.725,
"eval_steps_per_second": 4.566,
"step": 5184
},
{
"epoch": 55.0,
"grad_norm": 0.8289943933486938,
"learning_rate": 2.25e-05,
"loss": 0.0135,
"step": 5280
},
{
"epoch": 55.0,
"eval_LOCATION_f1": 0.9310344827586207,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9310344827586207,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9463722397476341,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9433962264150944,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.050759803503751755,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9536921151439299,
"eval_overall_precision": 0.9501246882793017,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.655,
"eval_samples_per_second": 259.528,
"eval_steps_per_second": 4.58,
"step": 5280
},
{
"epoch": 56.0,
"grad_norm": 0.4112291634082794,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.0132,
"step": 5376
},
{
"epoch": 56.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04709722474217415,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9522613065326633,
"eval_overall_precision": 0.9522613065326633,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6555,
"eval_samples_per_second": 259.349,
"eval_steps_per_second": 4.577,
"step": 5376
},
{
"epoch": 57.0,
"grad_norm": 0.5204743146896362,
"learning_rate": 2.15e-05,
"loss": 0.0125,
"step": 5472
},
{
"epoch": 57.0,
"eval_LOCATION_f1": 0.927038626609442,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9230769230769231,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.952076677316294,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9612903225806452,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04795367270708084,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6502,
"eval_samples_per_second": 261.467,
"eval_steps_per_second": 4.614,
"step": 5472
},
{
"epoch": 58.0,
"grad_norm": 0.026698121801018715,
"learning_rate": 2.1e-05,
"loss": 0.0137,
"step": 5568
},
{
"epoch": 58.0,
"eval_LOCATION_f1": 0.9322033898305084,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9483870967741935,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9671052631578947,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04820618778467178,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9535759096612295,
"eval_overall_precision": 0.9523809523809523,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6971,
"eval_samples_per_second": 243.88,
"eval_steps_per_second": 4.304,
"step": 5568
},
{
"epoch": 59.0,
"grad_norm": 0.42351385951042175,
"learning_rate": 2.05e-05,
"loss": 0.0113,
"step": 5664
},
{
"epoch": 59.0,
"eval_LOCATION_f1": 0.9316239316239315,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.923728813559322,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9517684887459807,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9673202614379085,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04612576961517334,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9559748427672956,
"eval_overall_precision": 0.9571788413098237,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.658,
"eval_samples_per_second": 258.372,
"eval_steps_per_second": 4.56,
"step": 5664
},
{
"epoch": 60.0,
"grad_norm": 0.09376300126314163,
"learning_rate": 2e-05,
"loss": 0.0122,
"step": 5760
},
{
"epoch": 60.0,
"eval_LOCATION_f1": 0.9276595744680851,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9159663865546218,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9483870967741935,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9671052631578947,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04772806912660599,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9534591194968555,
"eval_overall_precision": 0.9546599496221663,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.659,
"eval_samples_per_second": 257.958,
"eval_steps_per_second": 4.552,
"step": 5760
},
{
"epoch": 61.0,
"grad_norm": 0.21203207969665527,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.0112,
"step": 5856
},
{
"epoch": 61.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9487179487179488,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.961038961038961,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.049065276980400085,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9559748427672956,
"eval_overall_precision": 0.9571788413098237,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6687,
"eval_samples_per_second": 254.225,
"eval_steps_per_second": 4.486,
"step": 5856
},
{
"epoch": 62.0,
"grad_norm": 0.1659153401851654,
"learning_rate": 1.9e-05,
"loss": 0.0103,
"step": 5952
},
{
"epoch": 62.0,
"eval_LOCATION_f1": 0.927038626609442,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9230769230769231,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9456869009584665,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9548387096774194,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05345270037651062,
"eval_overall_accuracy": 0.9892945374691189,
"eval_overall_f1": 0.9522613065326633,
"eval_overall_precision": 0.9522613065326633,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6597,
"eval_samples_per_second": 257.678,
"eval_steps_per_second": 4.547,
"step": 5952
},
{
"epoch": 63.0,
"grad_norm": 0.08126848191022873,
"learning_rate": 1.85e-05,
"loss": 0.012,
"step": 6048
},
{
"epoch": 63.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9456869009584665,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9548387096774194,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04946228489279747,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9548872180451128,
"eval_overall_precision": 0.9525,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6631,
"eval_samples_per_second": 256.364,
"eval_steps_per_second": 4.524,
"step": 6048
},
{
"epoch": 64.0,
"grad_norm": 0.3278929591178894,
"learning_rate": 1.8e-05,
"loss": 0.0117,
"step": 6144
},
{
"epoch": 64.0,
"eval_LOCATION_f1": 0.927038626609442,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9230769230769231,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.930379746835443,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.930379746835443,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04906230419874191,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9450000000000001,
"eval_overall_precision": 0.9402985074626866,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.6603,
"eval_samples_per_second": 257.45,
"eval_steps_per_second": 4.543,
"step": 6144
},
{
"epoch": 65.0,
"grad_norm": 0.46427837014198303,
"learning_rate": 1.75e-05,
"loss": 0.0103,
"step": 6240
},
{
"epoch": 65.0,
"eval_LOCATION_f1": 0.9191489361702128,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.907563025210084,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.939297124600639,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9483870967741935,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.055914055556058884,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.9473684210526316,
"eval_overall_precision": 0.945,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.6527,
"eval_samples_per_second": 260.447,
"eval_steps_per_second": 4.596,
"step": 6240
},
{
"epoch": 66.0,
"grad_norm": 0.02081230841577053,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.0116,
"step": 6336
},
{
"epoch": 66.0,
"eval_LOCATION_f1": 0.9191489361702128,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.907563025210084,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.946031746031746,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9490445859872612,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05055687949061394,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.95,
"eval_overall_precision": 0.945273631840796,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6625,
"eval_samples_per_second": 256.609,
"eval_steps_per_second": 4.528,
"step": 6336
},
{
"epoch": 67.0,
"grad_norm": 0.09685682505369186,
"learning_rate": 1.65e-05,
"loss": 0.0105,
"step": 6432
},
{
"epoch": 67.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9423076923076923,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9545454545454546,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.046872638165950775,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9535759096612295,
"eval_overall_precision": 0.9523809523809523,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6603,
"eval_samples_per_second": 257.441,
"eval_steps_per_second": 4.543,
"step": 6432
},
{
"epoch": 68.0,
"grad_norm": 0.3742092549800873,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0097,
"step": 6528
},
{
"epoch": 68.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9453376205787781,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9607843137254902,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9799196787148594,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.976,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.049721281975507736,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.7244,
"eval_samples_per_second": 234.673,
"eval_steps_per_second": 4.141,
"step": 6528
},
{
"epoch": 69.0,
"grad_norm": 0.06661072373390198,
"learning_rate": 1.55e-05,
"loss": 0.0093,
"step": 6624
},
{
"epoch": 69.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9487179487179488,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.961038961038961,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04789399355649948,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9559748427672956,
"eval_overall_precision": 0.9571788413098237,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6619,
"eval_samples_per_second": 256.85,
"eval_steps_per_second": 4.533,
"step": 6624
},
{
"epoch": 70.0,
"grad_norm": 1.4071418046951294,
"learning_rate": 1.5e-05,
"loss": 0.0093,
"step": 6720
},
{
"epoch": 70.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9487179487179488,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.961038961038961,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04782553389668465,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9559748427672956,
"eval_overall_precision": 0.9571788413098237,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6623,
"eval_samples_per_second": 256.678,
"eval_steps_per_second": 4.53,
"step": 6720
},
{
"epoch": 71.0,
"grad_norm": 0.034226734191179276,
"learning_rate": 1.45e-05,
"loss": 0.01,
"step": 6816
},
{
"epoch": 71.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.952076677316294,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9612903225806452,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04436274617910385,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.9573934837092732,
"eval_overall_precision": 0.955,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.6791,
"eval_samples_per_second": 250.322,
"eval_steps_per_second": 4.417,
"step": 6816
},
{
"epoch": 72.0,
"grad_norm": 0.04642762243747711,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.0096,
"step": 6912
},
{
"epoch": 72.0,
"eval_LOCATION_f1": 0.9437229437229439,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9478260869565217,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.946031746031746,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9490445859872612,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04229244217276573,
"eval_overall_accuracy": 0.9917650288223991,
"eval_overall_f1": 0.957286432160804,
"eval_overall_precision": 0.957286432160804,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6709,
"eval_samples_per_second": 253.376,
"eval_steps_per_second": 4.471,
"step": 6912
},
{
"epoch": 73.0,
"grad_norm": 0.07104329764842987,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.0088,
"step": 7008
},
{
"epoch": 73.0,
"eval_LOCATION_f1": 0.94017094017094,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9322033898305084,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9517684887459807,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9673202614379085,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.0462079681456089,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9584905660377357,
"eval_overall_precision": 0.9596977329974811,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6627,
"eval_samples_per_second": 256.509,
"eval_steps_per_second": 4.527,
"step": 7008
},
{
"epoch": 74.0,
"grad_norm": 0.015769051387906075,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.01,
"step": 7104
},
{
"epoch": 74.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.946031746031746,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9490445859872612,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04767148569226265,
"eval_overall_accuracy": 0.9914905297831458,
"eval_overall_f1": 0.9548872180451128,
"eval_overall_precision": 0.9525,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6696,
"eval_samples_per_second": 253.867,
"eval_steps_per_second": 4.48,
"step": 7104
},
{
"epoch": 75.0,
"grad_norm": 0.036930594593286514,
"learning_rate": 1.25e-05,
"loss": 0.0083,
"step": 7200
},
{
"epoch": 75.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04896613955497742,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9522613065326633,
"eval_overall_precision": 0.9522613065326633,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.662,
"eval_samples_per_second": 256.778,
"eval_steps_per_second": 4.531,
"step": 7200
},
{
"epoch": 76.0,
"grad_norm": 0.015950500965118408,
"learning_rate": 1.2e-05,
"loss": 0.0085,
"step": 7296
},
{
"epoch": 76.0,
"eval_LOCATION_f1": 0.9322033898305084,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9426751592356688,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9487179487179487,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04817868396639824,
"eval_overall_accuracy": 0.9909415317046391,
"eval_overall_f1": 0.9525,
"eval_overall_precision": 0.9477611940298507,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6652,
"eval_samples_per_second": 255.565,
"eval_steps_per_second": 4.51,
"step": 7296
},
{
"epoch": 77.0,
"grad_norm": 0.48630064725875854,
"learning_rate": 1.1500000000000002e-05,
"loss": 0.0091,
"step": 7392
},
{
"epoch": 77.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9487179487179488,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.961038961038961,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.049579519778490067,
"eval_overall_accuracy": 0.9912160307438924,
"eval_overall_f1": 0.9560853199498118,
"eval_overall_precision": 0.9548872180451128,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6651,
"eval_samples_per_second": 255.589,
"eval_steps_per_second": 4.51,
"step": 7392
},
{
"epoch": 78.0,
"grad_norm": 0.03037888929247856,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.0083,
"step": 7488
},
{
"epoch": 78.0,
"eval_LOCATION_f1": 0.9316239316239315,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.923728813559322,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9517684887459807,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9673202614379085,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.976,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9682539682539683,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.047608185559511185,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9534591194968555,
"eval_overall_precision": 0.9546599496221663,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6622,
"eval_samples_per_second": 256.724,
"eval_steps_per_second": 4.53,
"step": 7488
},
{
"epoch": 79.0,
"grad_norm": 0.037008773535490036,
"learning_rate": 1.05e-05,
"loss": 0.0087,
"step": 7584
},
{
"epoch": 79.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9363057324840764,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9423076923076923,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.049399107694625854,
"eval_overall_accuracy": 0.9898435355476256,
"eval_overall_f1": 0.9510664993726474,
"eval_overall_precision": 0.949874686716792,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6669,
"eval_samples_per_second": 254.909,
"eval_steps_per_second": 4.498,
"step": 7584
},
{
"epoch": 80.0,
"grad_norm": 0.49808192253112793,
"learning_rate": 1e-05,
"loss": 0.0077,
"step": 7680
},
{
"epoch": 80.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9456869009584665,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9548387096774194,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05062989145517349,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6698,
"eval_samples_per_second": 253.817,
"eval_steps_per_second": 4.479,
"step": 7680
},
{
"epoch": 81.0,
"grad_norm": 0.24048176407814026,
"learning_rate": 9.5e-06,
"loss": 0.0086,
"step": 7776
},
{
"epoch": 81.0,
"eval_LOCATION_f1": 0.9276595744680851,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9159663865546218,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.926984126984127,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9299363057324841,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05177662894129753,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9438202247191011,
"eval_overall_precision": 0.9379652605459057,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.6576,
"eval_samples_per_second": 258.523,
"eval_steps_per_second": 4.562,
"step": 7776
},
{
"epoch": 82.0,
"grad_norm": 0.08680152893066406,
"learning_rate": 9e-06,
"loss": 0.0072,
"step": 7872
},
{
"epoch": 82.0,
"eval_LOCATION_f1": 0.9322033898305084,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.932475884244373,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9477124183006536,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05599362030625343,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9473684210526316,
"eval_overall_precision": 0.945,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.6532,
"eval_samples_per_second": 260.26,
"eval_steps_per_second": 4.593,
"step": 7872
},
{
"epoch": 83.0,
"grad_norm": 0.02610917203128338,
"learning_rate": 8.500000000000002e-06,
"loss": 0.008,
"step": 7968
},
{
"epoch": 83.0,
"eval_LOCATION_f1": 0.9191489361702128,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.907563025210084,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9456869009584665,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9548387096774194,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05147074535489082,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9498746867167919,
"eval_overall_precision": 0.9475,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6648,
"eval_samples_per_second": 255.707,
"eval_steps_per_second": 4.512,
"step": 7968
},
{
"epoch": 84.0,
"grad_norm": 0.03550398349761963,
"learning_rate": 8.000000000000001e-06,
"loss": 0.0062,
"step": 8064
},
{
"epoch": 84.0,
"eval_LOCATION_f1": 0.9191489361702128,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.907563025210084,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.952076677316294,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9612903225806452,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05295824259519577,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9523809523809523,
"eval_overall_precision": 0.95,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6533,
"eval_samples_per_second": 260.206,
"eval_steps_per_second": 4.592,
"step": 8064
},
{
"epoch": 85.0,
"grad_norm": 0.11215736716985703,
"learning_rate": 7.5e-06,
"loss": 0.0071,
"step": 8160
},
{
"epoch": 85.0,
"eval_LOCATION_f1": 0.9316239316239315,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.923728813559322,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9517684887459807,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9673202614379085,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.976,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9682539682539683,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.05237612873315811,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9534591194968555,
"eval_overall_precision": 0.9546599496221663,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6615,
"eval_samples_per_second": 256.973,
"eval_steps_per_second": 4.535,
"step": 8160
},
{
"epoch": 86.0,
"grad_norm": 0.03598828613758087,
"learning_rate": 7.000000000000001e-06,
"loss": 0.007,
"step": 8256
},
{
"epoch": 86.0,
"eval_LOCATION_f1": 0.927038626609442,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9230769230769231,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9456869009584665,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9548387096774194,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.976,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9682539682539683,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.054295916110277176,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.949748743718593,
"eval_overall_precision": 0.949748743718593,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.6597,
"eval_samples_per_second": 257.677,
"eval_steps_per_second": 4.547,
"step": 8256
},
{
"epoch": 87.0,
"grad_norm": 0.28171995282173157,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.0075,
"step": 8352
},
{
"epoch": 87.0,
"eval_LOCATION_f1": 0.9316239316239315,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.923728813559322,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9423076923076923,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9545454545454546,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9799196787148594,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.976,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.0545167475938797,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.950943396226415,
"eval_overall_precision": 0.9521410579345088,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.6556,
"eval_samples_per_second": 259.319,
"eval_steps_per_second": 4.576,
"step": 8352
},
{
"epoch": 88.0,
"grad_norm": 0.28649380803108215,
"learning_rate": 6e-06,
"loss": 0.0085,
"step": 8448
},
{
"epoch": 88.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9453376205787781,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9607843137254902,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.053749650716781616,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6493,
"eval_samples_per_second": 261.832,
"eval_steps_per_second": 4.621,
"step": 8448
},
{
"epoch": 89.0,
"grad_norm": 0.11110695451498032,
"learning_rate": 5.500000000000001e-06,
"loss": 0.009,
"step": 8544
},
{
"epoch": 89.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.053643494844436646,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9522613065326633,
"eval_overall_precision": 0.9522613065326633,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6632,
"eval_samples_per_second": 256.343,
"eval_steps_per_second": 4.524,
"step": 8544
},
{
"epoch": 90.0,
"grad_norm": 0.03984348103404045,
"learning_rate": 5e-06,
"loss": 0.0081,
"step": 8640
},
{
"epoch": 90.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05441142991185188,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9522613065326633,
"eval_overall_precision": 0.9522613065326633,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6649,
"eval_samples_per_second": 255.681,
"eval_steps_per_second": 4.512,
"step": 8640
},
{
"epoch": 91.0,
"grad_norm": 0.18129561841487885,
"learning_rate": 4.5e-06,
"loss": 0.0083,
"step": 8736
},
{
"epoch": 91.0,
"eval_LOCATION_f1": 0.94017094017094,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9322033898305084,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9453376205787781,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9607843137254902,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05335814505815506,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9559748427672956,
"eval_overall_precision": 0.9571788413098237,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6567,
"eval_samples_per_second": 258.888,
"eval_steps_per_second": 4.569,
"step": 8736
},
{
"epoch": 92.0,
"grad_norm": 0.20950916409492493,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0077,
"step": 8832
},
{
"epoch": 92.0,
"eval_LOCATION_f1": 0.94017094017094,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9322033898305084,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9517684887459807,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9673202614379085,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05391678586602211,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9584905660377357,
"eval_overall_precision": 0.9596977329974811,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6657,
"eval_samples_per_second": 255.384,
"eval_steps_per_second": 4.507,
"step": 8832
},
{
"epoch": 93.0,
"grad_norm": 0.020548459142446518,
"learning_rate": 3.5000000000000004e-06,
"loss": 0.0071,
"step": 8928
},
{
"epoch": 93.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9419354838709677,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9605263157894737,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05413615331053734,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9534591194968555,
"eval_overall_precision": 0.9546599496221663,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6652,
"eval_samples_per_second": 255.567,
"eval_steps_per_second": 4.51,
"step": 8928
},
{
"epoch": 94.0,
"grad_norm": 0.060379985719919205,
"learning_rate": 3e-06,
"loss": 0.0066,
"step": 9024
},
{
"epoch": 94.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9453376205787781,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9607843137254902,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05373545363545418,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6886,
"eval_samples_per_second": 246.876,
"eval_steps_per_second": 4.357,
"step": 9024
},
{
"epoch": 95.0,
"grad_norm": 0.2533499300479889,
"learning_rate": 2.5e-06,
"loss": 0.0073,
"step": 9120
},
{
"epoch": 95.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9483870967741935,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9671052631578947,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.0550670325756073,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.957286432160804,
"eval_overall_precision": 0.957286432160804,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6635,
"eval_samples_per_second": 256.216,
"eval_steps_per_second": 4.521,
"step": 9120
},
{
"epoch": 96.0,
"grad_norm": 0.054385554045438766,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.006,
"step": 9216
},
{
"epoch": 96.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9453376205787781,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9607843137254902,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05503709986805916,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6558,
"eval_samples_per_second": 259.231,
"eval_steps_per_second": 4.575,
"step": 9216
},
{
"epoch": 97.0,
"grad_norm": 0.08159766346216202,
"learning_rate": 1.5e-06,
"loss": 0.0068,
"step": 9312
},
{
"epoch": 97.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9389067524115756,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.954248366013072,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.054543741047382355,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9522613065326633,
"eval_overall_precision": 0.9522613065326633,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.8068,
"eval_samples_per_second": 210.7,
"eval_steps_per_second": 3.718,
"step": 9312
},
{
"epoch": 98.0,
"grad_norm": 1.2401155233383179,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.0072,
"step": 9408
},
{
"epoch": 98.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9453376205787781,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9607843137254902,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.054929181933403015,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6633,
"eval_samples_per_second": 256.3,
"eval_steps_per_second": 4.523,
"step": 9408
},
{
"epoch": 99.0,
"grad_norm": 0.11007474362850189,
"learning_rate": 5.000000000000001e-07,
"loss": 0.0062,
"step": 9504
},
{
"epoch": 99.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9453376205787781,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9607843137254902,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05416809394955635,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.7269,
"eval_samples_per_second": 233.877,
"eval_steps_per_second": 4.127,
"step": 9504
},
{
"epoch": 100.0,
"grad_norm": 0.26029637455940247,
"learning_rate": 0.0,
"loss": 0.0061,
"step": 9600
},
{
"epoch": 100.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9453376205787781,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9607843137254902,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.054102133959531784,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9547738693467337,
"eval_overall_precision": 0.9547738693467337,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.6638,
"eval_samples_per_second": 256.111,
"eval_steps_per_second": 4.52,
"step": 9600
},
{
"epoch": 100.0,
"step": 9600,
"total_flos": 4293597283743744.0,
"train_loss": 0.03807398425415158,
"train_runtime": 1160.6237,
"train_samples_per_second": 131.912,
"train_steps_per_second": 8.271
}
],
"logging_steps": 500,
"max_steps": 9600,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 500,
"total_flos": 4293597283743744.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}